Sorry, you need to enable JavaScript to visit this website.

Backdoor attacks against CNNs represent a new threat against deep learning systems, due to the possibility of corrupting the training set so to induce an incorrect behaviour at test time. To avoid that the trainer recognises the presence of the corrupted samples, the corruption of the training set must be as stealthy as possible. Previous works have focused on the stealthiness of the perturbation injected into the training samples, however they all assume that the labels of the corrupted samples are also poisoned.


Electric Network Frequency (ENF) analysis is a promising forensic technique for authenticating digital recordings and detecting tampering within the recordings. The validity of ENF analysis heavily relies on high-quality ENF signals extracted from multimedia recordings. In this paper, we propose an ENF signal extraction method for rolling shutter acquired videos using periodic zero-padding. Our analysis shows that the extracted ENF signals using the proposed method are not distorted and the component with the highest signal-to-noise ratio is located at the intrinsic frequency.


ENF (Electric Network Frequency) oscillates around a nominal value (50/60 Hz) due to imbalance between consumed and generated power. The intensity of a light source powered by mains electricity varies depending on the ENF fluctuations. These fluctuations can be extracted from videos recorded in the presence of mains-powered source illumination. This work investigates how the quality of the ENF signal estimated from video is affected by different light source illumination, compression ratios, and by social media encoding.


This work presents a reduced complexity image clustering (RCIC) algorithm that blindly groups images based on their camera fingerprint. The algorithm does not need any prior information and can be implemented without and with attraction, to refine clusters. After a camera fingerprint is estimated for each image in the data set, a fingerprint is randomly selected as reference fingerprint and a cluster is constructed using this fingerprint as centroid. The clustered fingerprints are removed from the data set and the remaining fingerprints are clustered repeating the same process.


In this work, we tackle this problem by firstly proposing CCTV-Fights, a novel and challenging dataset containing 1,000 videos of real fights, with more than 8 hours of annotated CCTV footage. Then we propose a pipeline, on which we assess the impact of different feature extractors, as well as different classifiers.


While significant work has been conducted to perform source cam- era model identification for images, little work has been done specif- ically for video camera model identification. This is problematic because different forensic traces may be left in digital images and videos captured by the same camera. As our experiments in this paper will show, a system trained to perform camera model identifi- cation for images yields unacceptably low performance when given video frames from the same cameras. To overcome this problem, new systems for identifying a videos source must be developed.